INDEX

Explanations

specific names and entities mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

historical references to significant figures and events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utterstock

-0.90

izontal

-0.86

iculty

-0.84

pection

-0.77

vc

-0.76

iminary

-0.75

atown

-0.74

 reuse

-0.74

 indic

-0.72

giene

-0.72

POSITIVE LOGITS

 Barack

1.37

 Adolf

1.31

 Bashar

1.30

 Winston

1.30

 Donald

1.28

 Osama

1.27

 LeBron

1.26

 George

1.26

 Muhammad

1.25

 Vladimir

1.25

Activations Density 1.292%

specific names and entities mentioned in the text

historical references to significant figures and events

No Comments

No Known Activations